1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
|
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.spark.examples.mllib;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;
// $example on$
import scala.Tuple2;
import org.apache.spark.api.java.JavaDoubleRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.mllib.linalg.Vectors;
import org.apache.spark.mllib.regression.LabeledPoint;
import org.apache.spark.mllib.regression.LinearRegressionModel;
import org.apache.spark.mllib.regression.LinearRegressionWithSGD;
// $example off$
/**
* Example for LinearRegressionWithSGD.
*/
public class JavaLinearRegressionWithSGDExample {
public static void main(String[] args) {
SparkConf conf = new SparkConf().setAppName("JavaLinearRegressionWithSGDExample");
JavaSparkContext sc = new JavaSparkContext(conf);
// $example on$
// Load and parse the data
String path = "data/mllib/ridge-data/lpsa.data";
JavaRDD<String> data = sc.textFile(path);
JavaRDD<LabeledPoint> parsedData = data.map(
new Function<String, LabeledPoint>() {
public LabeledPoint call(String line) {
String[] parts = line.split(",");
String[] features = parts[1].split(" ");
double[] v = new double[features.length];
for (int i = 0; i < features.length - 1; i++) {
v[i] = Double.parseDouble(features[i]);
}
return new LabeledPoint(Double.parseDouble(parts[0]), Vectors.dense(v));
}
}
);
parsedData.cache();
// Building the model
int numIterations = 100;
double stepSize = 0.00000001;
final LinearRegressionModel model =
LinearRegressionWithSGD.train(JavaRDD.toRDD(parsedData), numIterations, stepSize);
// Evaluate model on training examples and compute training error
JavaRDD<Tuple2<Double, Double>> valuesAndPreds = parsedData.map(
new Function<LabeledPoint, Tuple2<Double, Double>>() {
public Tuple2<Double, Double> call(LabeledPoint point) {
double prediction = model.predict(point.features());
return new Tuple2<>(prediction, point.label());
}
}
);
double MSE = new JavaDoubleRDD(valuesAndPreds.map(
new Function<Tuple2<Double, Double>, Object>() {
public Object call(Tuple2<Double, Double> pair) {
return Math.pow(pair._1() - pair._2(), 2.0);
}
}
).rdd()).mean();
System.out.println("training Mean Squared Error = " + MSE);
// Save and load model
model.save(sc.sc(), "target/tmp/javaLinearRegressionWithSGDModel");
LinearRegressionModel sameModel = LinearRegressionModel.load(sc.sc(),
"target/tmp/javaLinearRegressionWithSGDModel");
// $example off$
sc.stop();
}
}
|
